calibre/recipes/emg_rs.recipe

52 lines
2.2 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
emg.rs/vesti
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class emportal_rs(BasicNewsRecipe):
title = 'Ekonom:east Vesti'
__author__ = 'Darko Miletic'
description = 'Vasa dnevna doza poslovnih informacija iz Srbije, regiona i sveta. Vesti, Berze, Dogadaji, Casopisi.'
publisher = 'Ekonom:east Media Group'
category = 'Ekonom:east Media Group, Ekonomist, Budelar, Bankar, EMportal, Preduzeca, Moja Posla, EU praktikum, ekonomija, Srbija, Beograd, investicije, finansije, energetika, berza'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'sr'
remove_empty_feeds = True
masthead_url = 'http://www.emg.rs/img/emportal-rss.png'
extra_css = ' @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: Arial,Helvetica,sans1,sans-serif } .article_description{font-family: sans1, sans-serif} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
remove_tags = [dict(attrs={'class':['text-share']})]
keep_only_tags = [dict(attrs={'class':'text'})]
remove_tags_after = dict(attrs={'class':'text-share'})
remove_attributes = ['width','height']
feeds = [
(u'Srbija' , u'http://www.emg.rs/vesti/srbija/rss.xml')
,(u'Region' , u'http://www.emg.rs/vesti/region/rss.xml')
,(u'Svet' , u'http://www.emg.rs/vesti/svet/rss.xml' )
]
def print_version(self, url):
return url.replace('.html','.print.html')
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup